Yuyang Du

I am a Postdoctoral Fellow in Department of Information Engineering, The Chinese University of Hong Kong (CUHK). I received my Ph.D. degree in Information Engineering from the same institution, where I was supervised by Prof. Soung Chang Liew. I received my bachelor's degree from School of Electronics Engineering and Computer Science (EECS), Peking University (PKU), advised by Prof. Yiming Lei. I was a visiting scholar at Harvard in 2024-2025, and I was an research engineer at Hisilicon, Huawei in 2019-2020.

My research enables intelligence and connectivity in mobile edge systems. My work addresses two key challenges: 1) cost-effective generative AI for resource-constrained edge devices, and 2) reliable, low-latency communication for mobile applications.

Recently, I have focused on efficient LLM inference and task-oriented communication for intelligent manufacturing, which serves as a proof of concept for the feasibility and efficiency of mobile edge intelligence in dynamic, resource-constrained environments. My toolkit for building such systems includes AI, wireless communication, networking, and robotics.

News

2025-11: Distributed edge MoE inference framework OD-MoE is available on Arxiv.
2025-10: IndusGCC is accepted by NeurIPS'25 Workshop; KnowGuard is available on Arxiv.
2025-09: One paper about Industrial Robotic Network is available on Arxiv.
2025-08: LLMind 2.0, SA-OOSC, IndusGCC and VeriRAG are available on Arxiv.
2025-07: One paper about Generative Semantic Communication accepted by IEEE TMLCN.
2025-06: One paper about MLLM-assisted Data Mining is accepted by ICCV'25 Workshop.
2025-05: LMT++, a MLLM-empowered knowledge distillation framework, is accepted by IEEE TMI.
2025-04: Cellular-X, an LLM agent for cellular network, is accepted by Mobisys'25.
2025-03: One paper about Industrial IoT Reliability is accepted by IEEE TVT.
2025-02: RaC, a SFT framework for networking agents, is accepted by ICNC'25.
2025-01: LibraAlign, a DPO framework for ethical alignment, is available on Arxiv.